The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional Markdown files and templates. It does not include any executable scripts (Python, Node.js, Shell), system-level commands, or binary files that could pose a risk to the host environment.
[DATA_EXPOSURE]: The analysis found no hardcoded credentials, API keys, or references to sensitive configuration files such as .env, SSH keys, or cloud provider credentials.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external transcript text. While it lacks explicit boundary markers to isolate transcript content from instructions, the skill does not have any sensitive capabilities (such as network access or file system modification) that could be exploited via malicious text embedded in a transcript. The instructions emphasize strict fidelity to the original meaning, further mitigating risks.

transcript-polisher